F4Splat：基于前馈预测密度化的前馈式3D高斯溅射

摘要

前馈式3D高斯泼溅方法能够实现单次重建与实时渲染，但其通常采用固定的像素-高斯或体素-高斯映射流程，导致各视角间存在冗余的高斯分布。此外，现有方法缺乏在保持重建精度的同时控制高斯点总数量的有效机制。为解决这些局限性，我们提出F4Splat模型，通过前馈式预测性致密化策略，引入基于致密化得分的自适应分配机制，能够根据空间复杂度和多视角重叠情况动态调整高斯点分布。该模型通过预测区域致密化得分来估算所需高斯密度，并允许在不重新训练的情况下显式控制最终高斯点预算。这种空间自适应分配机制减少了简单区域的冗余分布，并最小化重叠视角间的重复高斯点，从而生成紧凑且高质量的3D表征。大量实验表明，相较于现有未校准的前馈方法，本模型在使用更少高斯点的同时，实现了更优异的新视角合成性能。

English

Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to redundant Gaussians across views. Moreover, they lack an effective mechanism to control the total number of Gaussians while maintaining reconstruction fidelity. To address these limitations, we present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting, introducing a densification-score-guided allocation strategy that adaptively distributes Gaussians according to spatial complexity and multi-view overlap. Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget without retraining. This spatially adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, producing compact yet high-quality 3D representations. Extensive experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods, while using significantly fewer Gaussians.

F4Splat：基于前馈预测密度化的前馈式3D高斯溅射

F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting

摘要

Support